From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756179Ab0JKUfs (ORCPT ); Mon, 11 Oct 2010 16:35:48 -0400 Received: from mx1.redhat.com ([209.132.183.28]:11771 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755726Ab0JKUfr (ORCPT ); Mon, 11 Oct 2010 16:35:47 -0400 Date: Mon, 11 Oct 2010 16:35:18 -0400 From: Don Zickus To: Peter Zijlstra Cc: Huang Ying , Ingo Molnar , "H. Peter Anvin" , linux-kernel@vger.kernel.org, Andi Kleen , Robert Richter Subject: Re: [PATCH -v3 3/6] x86, NMI, Rewrite NMI handler Message-ID: <20101011203518.GB24567@redhat.com> References: <1286606987-19879-1-git-send-email-ying.huang@intel.com> <1286606987-19879-3-git-send-email-ying.huang@intel.com> <1286813635.2336.617.camel@twins> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <1286813635.2336.617.camel@twins> User-Agent: Mutt/1.5.21 (2010-09-15) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Mon, Oct 11, 2010 at 06:13:55PM +0200, Peter Zijlstra wrote: > On Sat, 2010-10-09 at 14:49 +0800, Huang Ying wrote: > > notify_die(DIE_NMI_IPI); > > notify_die(DIE_NMI); > > /* process io port 0x61 */ > > nmi_watchdog_touch(); > > unknown_nmi(); > > Why keep NMI_IPI? What the heck is it for? > > I'd like to see: > > DIE_NMI > DIE_NMI_UNKNOWN > > In DIE_NMI we walk the chain and deal with NMIs, in DIE_NMI_UNKNOWN we > try to consume extra NMIs where possible (like the much discussed extra > PMU interrupts). Yeah, there was another much discussed thread about creating an NMI notifier chain (instead of using the die_chain). And then re-arrange handlers according to a priority scheme. I wouldn't mind have Ingo commit most of this patchset to a temporary work-in-progress branch and have us build more changes on top. A lot of these changes are a good stepping stone towards simplifying things. Cheers, Don